English

Memory Guided Road Detection

Computer Vision and Pattern Recognition 2021-06-29 v1

Abstract

In self driving car applications, there is a requirement to predict the location of the lane given an input RGB front facing image. In this paper, we propose an architecture that allows us to increase the speed and robustness of road detection without a large hit in accuracy by introducing an underlying shared feature space that is propagated over time, which serves as a flowing dynamic memory. By utilizing the gist of previous frames, we train the network to predict the current road with a greater accuracy and lesser deviation from previous frames.

Keywords

Cite

@article{arxiv.2106.14184,
  title  = {Memory Guided Road Detection},
  author = {Praveen Venkatesh and Rwik Rana and Varun Jain},
  journal= {arXiv preprint arXiv:2106.14184},
  year   = {2021}
}
R2 v1 2026-06-24T03:38:14.506Z